Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2016 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0516. Min Act: -0.0002

Data Index: 1476811 (Python Code)

Max Activating Token Index: 95

Text #1

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0491. Min Act: -0.0003

Data Index: 1376349 (Python Code)

Max Activating Token Index: 328

Text #2

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0445. Min Act: -0.0003

Data Index: 985922 (C4 (Web Text))

Max Activating Token Index: 838

Text #3

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0464. Min Act: -0.0003

Data Index: 31601 (C4 (Web Text))

Max Activating Token Index: 138

Text #4

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0463. Min Act: -0.0003

Data Index: 1492483 (Python Code)

Max Activating Token Index: 42

Text #5

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0450. Min Act: -0.0002

Data Index: 1025311 (C4 (Web Text))

Max Activating Token Index: 756

Text #6

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0454. Min Act: -0.0002

Data Index: 534804 (C4 (Web Text))

Max Activating Token Index: 736

Text #7

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0432. Min Act: -0.0003

Data Index: 1624983 (Python Code)

Max Activating Token Index: 14

Text #8

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1361995 (Python Code)

Max Activating Token Index: 689

Text #9

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0430. Min Act: -0.0003

Data Index: 904765 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0444. Min Act: -0.0002

Data Index: 369657 (C4 (Web Text))

Max Activating Token Index: 906

Text #11

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0419. Min Act: -0.0004

Data Index: 655357 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0431. Min Act: -0.0003

Data Index: 1602589 (Python Code)

Max Activating Token Index: 117

Text #13

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0428. Min Act: -0.0003

Data Index: 1386934 (Python Code)

Max Activating Token Index: 718

Text #14

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0426. Min Act: -0.0003

Data Index: 374568 (C4 (Web Text))

Max Activating Token Index: 246

Text #15

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0433. Min Act: -0.0003

Data Index: 1555003 (Python Code)

Max Activating Token Index: 344

Text #16

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0411. Min Act: -0.0003

Data Index: 1410770 (Python Code)

Max Activating Token Index: 227

Text #17

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0409. Min Act: -0.0003

Data Index: 1543774 (Python Code)

Max Activating Token Index: 91

Text #18

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0407. Min Act: -0.0003

Data Index: 140916 (C4 (Web Text))

Max Activating Token Index: 585

Text #19

Max Range: 0.0516. Min Range: -0.0516

Max Act: 0.0391. Min Act: -0.0003

Data Index: 1466008 (Python Code)

Max Activating Token Index: 539